Search Results (141)

Background: Megaprosthetic reconstruction is the standard of care for limb salvage after tumor resection around the knee, but the full burden of unplanned revision surgery is rarely reported as a structured composite outcome. We evaluated 241 consecutive patients over 21 years at a tertiary orthopedic oncology center. Methods: This retrospective cohort included 241 patients (160 distal femur, 78 proximal tibia, three combined) treated between 2003 and 2024. Revision-free survival (RFS, composite of any unplanned revision or amputation) and amputation-free survival were estimated by Kaplan–Meier analysis; independent predictors were identified by Cox regression. A pre-specified major-event composite (amputation, implant removal, or recurrence resection) was used for sensitivity analysis. Results: Mean age was 34.9 ± 19.5 years; mean follow-up was 120.2 months. Negative resection margin (R0) was achieved in 85.5% (206/241). Unplanned revision was required in 25 patients (10.4%); overall limb salvage was 92.9%. Five-year RFS was 73.8% (distal femur) vs. 65.0% (proximal tibia; p = 0.084), and 5-year limb salvage was 88.9% vs. 84.3% (p = 0.081). Surgical margin was strongly associated with outcome: 5-year RFS 75.4% (R0) vs. 48.7% (R1/R2; p < 0.001); 5-year limb salvage 90.6% vs. 71.5% (p = 0.003). On exploratory multivariate Cox analysis, proximal tibia site and positive margin were associated with worse revision-free survival; within the proximal tibia subgroup, absence of gastrocnemius flap coverage was also associated with worse outcome (interpreted with caution given the small flap subgroup, n = 11, and limited event count). Conclusions: In this single-center series, megaprosthetic reconstruction around the knee achieved acceptable revision-free survival and limb salvage. Surgical margin status was the strongest independent predictor of both endpoints, reinforcing the well-established importance of oncologic margin quality and site-specific soft tissue strategies. Full article

Background: Coronary computed tomography angiography (cCTA) is now indicated as a non-invasive tool for ruling out obstructive coronary artery disease (O-CAD) in patients who are candidates for transcatheter aortic valve implantation (TAVI) showing low-intermediate pre-test probability of O-CAD. In elderly and comorbid TAVI candidates, the safety and accuracy of cCTA as an alternative to invasive coronary angiography (ICA) for ruling out O-CAD remain to be established. Aim: To assess the feasibility, diagnostic accuracy, and clinical safety of cCTA for ruling out proximal O-CAD in elderly, comorbid, high-risk patients undergoing TAVI. Methods: We conducted a retrospective, single-center study including all consecutive patients with severe symptomatic aortic stenosis who underwent TAVI between January 2019 and December 2020. All patients underwent pre-TAVI cCTA. Patients with positive or non-diagnostic cCTA underwent ICA selectively (ICA group). In patients with no-O-CAD, ICA was omitted and proceeded directly to TAVI (no-ICA group). Accordingly, patients were divided into two groups: no-ICA and ICA group. Clinical follow-up was extended up to 5 years, with assessment of major adverse cardiovascular events (MACEs), mortality, heart failure hospitalizations, and unplanned revascularization. Results: Among 355 patients enrolled, 210 were included in the study. Among them, 140 (66.7%) had negative cCTA for O-CAD, and ICA was safely omitted in 132 patients (62.8%). cCTA was inconclusive in 43 patients (20.5%) and positive in 27 (12.9%). ICA confirmed O-CAD in 53 of 78 patients (67.9%) and PCI was performed in 35 of 53 (66.0%). The accuracy of cCTA for ruling in O-CAD was low (66.28%). During the follow-up period (1513 ± 508 days), the no-ICA group showed comparable outcomes to the ICA group in terms of periprocedural complications and long-term results—at both 1 and 5 years—for MACEs, heart failure hospitalizations, mortality and unplanned revascularization. Outcomes remain comparable between the two groups after performing matched-pair analyses. Conclusions: Our data show that cCTA may provide a reliable, safe, and effective alternative to ICA for ruling out obstructive CAD in elderly patients undergoing TAVI when image quality is diagnostic. A cCTA-based strategy allows deferral of ICA in most cases without compromising procedural safety or long-term clinical outcomes, enabling a personalized and tailored clinical pathway. Whether advanced CT techniques, such as CT-FFR and photon-counting CT, may help refine patient selection for invasive coronary assessment remains to be demonstrated. Full article

Purpose: Traditional plaster and fiberglass casts remain widely used for fracture immobilization but are associated with recognized challenges, including skin irritation, hygiene limitations, and distress during cast removal, particularly in pediatric populations. Light-cured polymer immobilization (LCPI) systems have been introduced as an alternative method of fracture support. The primary objective of this study was to describe radiographic healing and alignment outcomes among patients treated with an LCPI system. Secondary objectives were to document skin- and device-related events and to identify any unplanned removals or subsequent re-interventions. Methods: A 6-month retrospective cohort study was conducted involving 108 consecutive patients treated with an LCPI system between January and June 2025 at a single orthopaedic clinic. Clinical and radiographic records were reviewed to extract demographic information, injury characteristics, treatment details, immobilization duration, healing outcomes, alignment status, and recorded adverse events. Outcomes were summarized using descriptive statistics. Results: Immobilization was applied for 104 fractures (96.3%), three sprains (2.8%), and one elbow dislocation (0.9%). The cohort (76 males, 32 females; mean age: 13.4 years; range: 4–53) demonstrated radiographic union or progression toward union among fracture cases with available follow-up imaging. Mean immobilization duration was 29.2 days (SD: 6.2; range: 10–48). Alignment at device removal was documented as anatomic or near-anatomic in 103 of 104 fractures (99.1%) based on treating clinician assessment (99.1%). Device breakage was documented in 12 cases (11.1%), of which 3 required additional immobilization. Two patients (1.9%) experienced mild cutaneous reactions that resolved with conservative management. No severe device-related complications were documented. Conclusions: Healing outcomes and recorded adverse events were consistent with expected clinical patterns for this patient population in this descriptive retrospective cohort of patients treated with an LCPI system. These findings provide descriptive real-world data regarding clinical utilization and short-term outcomes in selected patients. Prospective comparative studies are needed to further define effectiveness, safety, cost considerations, and broader applicability across diverse fracture populations. Full article

Natural disasters and extreme meteorological events are primary causes of unplanned outages in modern power systems. Existing early warning methods suffer from insufficient non-linear feature extraction, severe class imbalance, and limited minority-class recall under single-classifier architectures. This paper proposes a seven-class meteorological fault early warning framework that integrates a sparse autoencoder (SAE), a G1–entropy composite weighting scheme, SMOTE oversampling, and a soft-voting BP–XGBoost ensemble. A leakage-free experimental protocol confines SMOTE exclusively to the training partition, eliminating data contamination from evaluation. Validated on 1955 fault records from a regional grid in East China covering 110 kV, 220 kV, and 500 kV voltage levels (2013–2022), the proposed framework achieved 96.42% accuracy and a 97.46% macro F1-score on the held-out test set, outperforming SVM (72.68%), Random Forest (89.31%), LSTM (81.47%), 1D-CNN (85.38%), and LightGBM (92.15%). Ablation experiments confirmed that SMOTE and G1–entropy weighting contributed macro F1 gains of 8.34 and 6.91 percentage points, respectively, while removing the XGBoost branch degraded accuracy by 28.25%. Temporal validation on 2019–2022 records yielded 91.57% accuracy, confirming temporal generalization. Error analysis further revealed that bidirectional misclassification between lightning damage and wind damage, rooted in shared atmospheric instability signatures, constitutes the dominant residual error source, providing theoretical guidance for future threshold optimization strategies. Full article

Background: Patients with type 2 diabetes mellitus (T2DM) undergoing cardiac surgery represent a high-risk population characterized by substantial cardiometabolic stress and increased susceptibility to postoperative heart failure, renal dysfunction, and unplanned rehospitalization. Although sodium-glucose cotransporter 2 (SGLT2) inhibitors provide established cardiorenal protection in ambulatory populations, their perioperative impact in cardiac surgery cohorts remains insufficiently defined. Methods: In a single-center retrospective cohort of 620 T2DM patients, inverse probability of treatment weighting and time-dependent Cox regression were applied to account for perioperative treatment interruption and delayed postoperative reinitiation when evaluating the association between chronic SGLT2 inhibitor therapy and 12-month rehospitalization risk. To provide biological context for the observed clinical associations, target-driven systems pharmacology, molecular docking against SGLT2, NHE1, AMPK, and NLRP3, and protein–protein interaction (PPI) network analysis were performed. Hub proteins were identified using Maximal Clique Centrality, followed by functional enrichment (GO/KEGG) analysis. Results: Chronic SGLT2 inhibitor therapy was associated with reduced first rehospitalization (HR 0.64; 95% CI 0.48–0.85; p = 0.002) and a lower cumulative rehospitalization burden (IRR 0.61; 95% CI 0.46–0.82; p = 0.001), primarily driven by heart failure-related and metabolic phenotypes. Molecular docking analyses identified favorable binding with SGLT2 and additional cardiometabolic and inflammatory targets, including NHE1, AMPK, NLRP3, IKKβ, IL-6Rα, and PPAR isoforms, suggesting modulation of myocardial ion homeostasis, metabolic resilience, and inflammatory signaling. PPI analysis identified eight hub proteins (AKT1, MTOR, STAT3, EGFR, PIK3CA, SRC, MAPK1, and MAPK3) significantly enriched in PI3K/AKT, MAPK/ERK, and ErbB signaling pathways. Conclusions: Chronic SGLT2 inhibitor therapy was independently associated with reduced postoperative rehospitalization and cumulative event burden in T2DM patients undergoing cardiac surgery. Integrated in silico analyses offer mechanistic hypotheses consistent with the observed clinical associations. These findings suggest that structured perioperative SGLT2 inhibitor management may contribute to improved postoperative outcomes, while prospective validation in future studies would strengthen these findings. However, given the retrospective observational design, these findings should be interpreted as associative rather than causal. Full article

Background/Objectives: Stress echocardiography (SE) had been recommended by professional societies for assessing patients with suspected angina. SE protocols are variable across hospitals and countries in the recommendation of the cessation of rate-controlling medication (RCMx) prior to SE. Some expert opinion papers recommend the cessation of beta receptor blockers (BBs) and rate-controlling calcium channel blockers 48 h prior to SE to improve the diagnostic accuracy of the test. There is no evidence that the continuation of RCMx can affect the outcome of SE and short-term major adverse cardiovascular events (MACEs). To investigate the efficacy of Dobutamine SE in a cohort of patients where the cessation of rate-controlling medication has not been mandated, we reviewed our data over a one-year period in patients investigated for suspected coronary artery disease (CAD). Methods: A retrospective data analysis was performed on 227 consecutive patients who underwent Dobutamine SE between January 2022 and January 2023 in a single centre. In addition to dobutamine, the protocol allowed the administration of intravenous atropine (maximum dose of 1.2 mg) and a “top up” handgrip exercise at the discretion of the performing cardiologist. We assessed the Dobutamine SE outcome (positive vs. negative), target heart rate (THR, 85% of maximum age predicted), and the achieved peak HR in the two groups with RCMx and without RCMx. We analysed the patients’ characteristics and 12-month outcomes of a combined MACE of death, non-fatal MI, stroke, admission with angina, and unplanned revascularisation. Results: Of the 227 patients, 61% were on No-RCMx (male 40%). Ninety-three percent of the patients on RCMx were on BB and 7% on other rate-controlling medications. The THR was achieved in 74% of the patients with-RCMx and 90% in the without-RCMx groups p = 0.0018. Positive Dobutamine SE was observed in 48% (43/89) of patients on RCMx vs. 28% (39/138) on No-RCMx (p = 0.0022). Patients who did not reach THR 43% (16/37) had positive Dobutamine SE compared to 35% (66/190) who reached THR (p = 0.626). There was no difference between groups in the peak WMSI. Logistic regression analysis showed that being on RCMx was independently associated with positive Dobutamine SE (OR 2.03, 95% CI 1.06–3.91, and p = 0.034). The MACE rate was higher in patients where the THR was not achieved (9/37, 24.0%) vs. where THR was achieved (9/190, 4.7%), p < 0.001, in both the with-RCMx (7/30, 23% vs. 6/66, 9.1%, p = 0.013) and without-RCMx (2/14, 14% vs. 3/124, 2.4%; p = 0.025) groups, respectively. RCMx was independently associated with MACE (OR 3.68, 95% CI 1.227–11.046, and p = 0.020). Conclusions: The use of RCMx proved to be a predictor of both SE and MACE outcomes irrespective of the achieved THR. Our data supports the practice that patients referred for Dobutamine SE on RCMx can continue taking them without impact on the test accuracy. Full article

Implantable Cardioverter-Defibrillators (ICDs) are life-sustaining devices used in the prevention of sudden death in patients suffering from advanced cardiac diseases. Although improvements in ICD technology and monitoring capabilities have been made, existing techniques are still not effective in predicting accelerated battery drain, thereby causing unplanned generator replacement and clinically significant device-related events. In this study, machine learning techniques were employed in the assessment of the early detection of ICD battery depletion risk using the collected device interrogation reports. The dataset used consisted of 32 devices in the training set and nine in the testing set. In order to mitigate the problem of a small sample size, a GMM-based data augmentation technique was applied solely to the training data, and actual devices were used for the testing data. Five supervised models, including Logistic Regression, Random Forest, SVM, CatBoost, and a Neural Network (MLP), have been utilized using a repeated stratified cross-validation and a separate held-out test data set. All the models have been tested for their performance using classification metrics. All models demonstrated variable performance with wide confidence intervals due to limited sample size. Support vector machines showed the highest cross-validation discrimination 0.889 ± 0.203, though uncertainty remains substantial given the small datasets (n = 41). From the feature analysis, it was found that atrial sensing amplitude, RV/LV capture threshold, output settings, and implant duration were the most important features for the prediction of high battery depletion risk. These findings suggest that changes in device parameters and implant age are associated with elevated battery depletion risk, supporting the feasibility of telemetry-driven risk stratification for device management. Full article

This paper investigates the optimization of maintenance strategies to improve the reliability of equipment at the Kapshagay Hydropower Plant (HPP), located in Kazakhstan. Operational data for the period 2020–2025 were analyzed to evaluate the effectiveness of existing maintenance systems. The analysis showed that the failure frequency of the main equipment averaged 3.8–4.2 events per year, while annual unplanned downtime reached 80–100 h, resulting in electricity generation losses of 2.5–3.2%. In addition, total maintenance costs were approximately 150 million KZT per year, with about 40% related to unplanned repairs. A reliability-centered maintenance model was developed using mathematical modeling and simulation tools such as Python 3.11 and SMath Solver 0.99.7920. The study integrates reliability theory, exponential failure modeling, and statistical performance analysis based on operational data from the Kapshagay HPP. Simulation-based validation was performed to compare baseline and optimized maintenance strategies under real operating conditions. After implementing the proposed model, equipment failure probability decreased by 15%, failure rate decreased by 28%, the mean time between failures increased from 120 days to 165 days, and repair duration decreased from 6 days to 4 days. Additionally, failure probability decreased from 0.10 to 0.07, while annual downtime decreased from 6.2 days to 4.1 days. Electricity generation losses decreased by approximately 18–22 GWh per year, while the annual economic benefit was estimated at 320–480 million KZTn. The results demonstrate that reliability-centered maintenance can increase equipment reliability by 20–30%, reduce maintenance costs by 10–12%, and improve electricity generation efficiency by 1.8–2.4%. The obtained results have practical significance for improving the technical and economic performance of hydropower plants. Full article

Background: Sodium–glucose cotransporter 2 inhibitors (SGLT2i) reduce mortality and morbidity in patients with heart failure (HF). However, their efficacy and safety in underweight patients remain uncertain. This study aimed to evaluate the efficacy and safety of SGLT2i in underweight patients with HF. Methods: This study was a single-center, prospective observational study designed to assess the efficacy of SGLT2i therapy in underweight patients with HF. The primary outcome was a composite of unplanned hospitalization for HF or death from cardiovascular causes. A key secondary outcome was hospitalization from any cause. Results: This study enrolled 131 consecutive patients with a body mass index (BMI) > 18.5 kg/m² hospitalized for HF between December 2020 and October 2023. The median age of the study population was 81 (73–87) years, and 60% were female. Baseline BMI was 17.2 (16.0–17.9) kg/m². Of these, 28 patients initiated SGLT2i during index hospitalization, while the remaining 103 did not receive SGLT2i. Over a median of 20.4 months of follow-up, the primary outcome occurred in 6 of 28 patients (21.4%) with SGLT2i and 22 of 103 patients (21.4%) without SGLT2i (p = 0.758). All-cause hospitalizations occurred in 23 of 28 patients (82.1%) with SGLT2i and 65 of 103 patients (63.1%) without SGLT2i (p = 0.009). Patients receiving SGLT2i showed a significant decrease in BMI at discharge, 1 month after discharge, and 3 months after discharge compared with those without SGLT2i (p < 0.05 for each time point). Conclusions: SGLT2i in underweight patients with HF may not reduce cardiovascular event risk and may be associated with a higher rate of overall hospitalizations. Full article

Background: Liver cirrhosis is a systemic disease characterized by progressive hepatic dysfunction and frequent decompensation events. Conventional prognostic models such as the Child–Turcotte–Pugh (CTP) and Model for End-stage Liver Disease (MELD) scores primarily reflect liver-specific severity and may not fully capture the multidimensional vulnerability of patients with cirrhosis. Frailty, a syndrome reflecting reduced physiological reserve, has emerged as a potential prognostic marker in this population. Methods: In this prospective single-center cohort study, 134 patients with liver cirrhosis were enrolled between March and October 2021 and followed at three-month intervals. Frailty was assessed at baseline using the Fried Frailty Index (FFI). Patients were categorized as fit/prefrail or frail. The primary endpoints were cirrhosis-related complications, unplanned hospitalizations, and all-cause mortality. Associations between frailty, its individual components, and clinical outcomes were evaluated. Results: Frailty was present in 41% of patients. Frail patients were older and had higher MELD and CTP scores. During follow-up, frailty was significantly associated with higher rates of ascites (p < 0.001), hepatic encephalopathy (p < 0.001), hepatorenal syndrome (p < 0.001), spontaneous bacterial peritonitis (p = 0.01), and unplanned hospitalizations (p < 0.001). Mortality occurred in 22% of frail patients compared with 3.8% in non-frail patients (p < 0.001). Each frailty component, including reduced grip strength, slow gait speed, low physical activity, exhaustion, and unintentional weight loss, was independently associated with adverse outcomes. Conclusions: Frailty, as assessed by the Fried Frailty Index, is a strong predictor of complications, hospitalization, and mortality in patients with liver cirrhosis. Incorporating frailty assessment into routine clinical practice may improve risk stratification and guide long-term management strategies. Full article

Hospitals are energy- and waste-intensive systems. Inpatient buildings dominate the sector’s electricity and gas consumption, and healthcare waste streams—especially device-associated disposables—increase environmental burdens. AI-enabled predictive maintenance (PdM) offers a dual lever: (1) reducing energy use by keeping assets operating at efficient points, and (2) preventing avoidable waste by extending component life, reducing emergency spares, and avoiding device-induced clinical workflow disruptions. In this study, an end-to-end architecture is developed by integrating multi-modal sensing (electrical, thermal, acoustic, vibration), computerized maintenance management systems (CMMS), risk-based maintenance under International Electrotechnical Commission (IEC)/International Organization for Standardization standards (ISO 60601, 62353/62304, 81001-5-1), and learning pipelines (self-supervised anomaly detection, remaining useful life estimators, and carbon-aware work order scheduling). Using representative hospital archetypes and equipment classes (imaging, patient monitoring, laboratory analyzers, sterilizers, and pumps), energy, downtime, and waste avoidance are simulated under baseline preventive maintenance (PM) versus PdM with alternate equipment management. Results showed that 10–22% site electricity reduction was achieved, attributable to equipment efficiency and optimized duty-cycling, 18–35% fewer unplanned failures, and a 12–28% reduction in associated consumable waste and emergency part scrappage across scenarios, while maintaining compliance with Joint Commission/Centers for Medicare & Medicaid Services and IEC safety testing intervals. We discuss cybersecurity (IEC 81001-5-1) and the trustworthiness of AI, present a governance model linking CMMS events to carbon telemetry, and provide an implementation roadmap. Full article

Flooding is one of the major natural disasters that have a major impact on urban areas due to the increasing intensity of factors like extreme weather conditions, climate change, and unplanned urbanization. Considering Cook County, Illinois, the rapid development of the region, flat topography, and the induced rainfall extremes from climate change increase the potential risk of flooding when interacting with dense urban exposure and infrastructure. This study employed the Frequency Ratio (FR) model in a GIS environment to create a high-resolution flood susceptibility map of the county. The map was developed using 281 historical flood points collected from several authoritative sources, such as National Oceanic and Atmospheric Administration (NOAA) Storm Events Database records, Federal Emergency Management Agency (FEMA) Flood Insurance Study (FIS) and Flood Insurance Rate Map (FIRM)-based FIRMette products, and U.S. Geological Survey (USGS) flood-inundation studies. Thirteen conditioning factors, including land use, elevation, slope, soil drainage, rainfall, and distance to the stream, were used to calculate FR values and to develop the Flood Susceptibility Index (FSI). The resulting FSI was grouped into four susceptibility zones: low, medium, high, and very high. The findings indicated that more than 64% of Cook County has a high and very high risk of flood susceptibility, particularly in the vicinity of major river corridors. The model was validated using testing data with a 91.4% prediction accuracy, which also demonstrated the reliability and applicability of the FR model in the urban flood susceptibility assessment. The map serves as a valuable tool for risk-based urban planning and design of flood mitigation infrastructure in one of the most populated counties in the United States. Full article

Background: Clinicians rely on clinical judgement and vital sign monitoring to identify patient deterioration, commonly supported by systems such as the National Early Warning Score 2 (NEWS2). However, NEWS2 is associated with a high false-positive burden, contributing to alert fatigue in increasingly pressured clinical environments. Consequently, there is a growing need for early warning systems (EWS) that not only detect deterioration but do so with higher precision to prioritise clinically meaningful alerts. We aimed to develop and validate a prognostic EWS capable of predicting real-time clinical deterioration in hospitalised adult patients. Methods: We conducted a retrospective observational cohort study using routinely collected Electronic Patient Record (EPR) data. A Cox proportional hazards model with time-varying covariates was developed to estimate dynamic risk of deterioration. Deterioration was defined as unplanned transfer to intensive care, unplanned surgery, or in-hospital death. Data for model development comprised 37,989 adult inpatient episodes admitted between January 2022 and October 2024, and were initially split into training, temporal validation and test datasets. An extended evaluation period included 11,048 patients admitted through September 2025. Model performance was compared with NEWS2 at the emergency-response threshold (≥7). Results: The final model produced a tiered “traffic-light” risk profile and demonstrated substantially higher precision than NEWS2 while maintaining comparable recall in our test data. At the red alert threshold, precision was 60% compared with 16% for NEWS2 ≥7, with 82% versus 43% of alerts occurring within 24 h of deterioration. Performance remained consistent across the extended evaluation period. Conclusions: A survival-based EWS incorporating time-varying covariates achieved higher precision and improved temporal alignment with deterioration events compared with NEWS2. A tiered amber–red alert framework may support more targeted escalation, reduce alert fatigue, and enhance early identification of clinical deterioration. Full article

Background: Unplanned hospital readmission after surgical treatment of primary spinal infections (PSIs) represents a major clinical and economic burden. Despite the fact that advances in surgical and antimicrobial management have been made, risk stratification for early and late readmissions remains poorly defined. Objective: We aimed to explore the clinical, microbiological, and perioperative characteristics potentially associated with 30-day, 90-day, and 1-year unplanned readmissions following the surgical treatment of PSIs in adult patients. Methods: A retrospective cohort study was performed that included adult patients who underwent surgery for primary spinal infections between January 2017 and December 2023 at our tertiary referral center. Demographics, comorbidities, laboratory parameters, microbiological profiles, and postoperative outcomes were analyzed. Associations between candidate variables and readmission were explored using univariate statistical analyses; multivariable modeling was not performed due to the low number of readmission events. Results: In total, seventy-nine patients (mean age 62.2 ± 12.7 years; 38% female) were included. The in-hospital mortality rate was 5.1%; at 1-year follow-up, 10.3% of patients were readmitted and 5.9% required reoperation; and Staphylococcus aureus was the most common isolated pathogen. No independent variables demonstrated a statistically significant association with readmission. However, trends toward higher readmission were observed in patients with liver disease, hypoalbuminemia, and postoperative transfusion. Conclusions: In this exploratory single-center cohort, the low number of readmission events limited statistical power and precluded adjusted modeling. Univariate analyses did not identify statistically significant associations between the evaluated variables and 30-day, 90-day, or 1-year readmission; therefore, the results should be interpreted cautiously as hypothesis-generating. Larger prospective multicenter studies with adequate event counts are needed to support adjusted risk stratification approaches. Until such tools are available, close postoperative follow-up across all PSI patients is necessary. Full article

The mining industry relies heavily on large-scale machinery, making operational efficiency highly sensitive to equipment breakdowns and maintenance interruptions. Such breakdowns directly affect production performance, operational costs, and planning accuracy. Therefore, the ability to predict machinery downtime particularly for haul trucks, loaders, drilling machinery, and dozers used in open-pit operations is essential for improving productivity and ensuring reliable mine planning. This study aims to predict machinery breakdowns and estimate the annual total number of breakdowns using machine-learning techniques applied to a fully digitalized dataset of 16,027 breakdown and maintenance records collected from an open-pit coal mine. A Random Forest classification model was developed to identify the breakdown unit for each event, achieving an accuracy of 94%, while a Random Forest regression model estimated the annual breakdown counts with an R² value of 0.98. In addition, the relationships between breakdown frequency and key production indicators were examined using linear regression and correlation analyses. The results show a strong association between run-of-mine quantities and coal production, a moderate relationship between stripping activity and breakdown frequency, and negligible linear relationships between breakdowns and production volumes. Overall, the findings demonstrate that integrating machine-learning models with operational mining data can significantly enhance predictive maintenance, reduce unplanned downtime, and improve production planning in open-pit mining operations. Full article